作者: K. Julisch
DOI: 10.1109/ACSAC.2001.991517
关键词:
摘要: It is a well-known problem that intrusion detection systems overload their human operators by triggering thousands of alarms per day. As matter fact, IBM Research's Zurich Research Laboratory has been asked one our service divisions to help them deal with this problem. This paper presents the results research, validated thanks large set operational data. We show should be managed identifying and resolving root causes. Alarm clustering introduced as method supports discovery The general alarm proved NP-complete, an approximation algorithm proposed, experiments are presented.